Rare Life Event Detection via Mobile Sensing Using Multi-Task Learning
This work addresses the problem of detecting infrequent life events for mental health monitoring, but it is incremental as it builds on existing multi-task learning approaches.
The paper tackled detecting rare life events from mobile sensing data to aid mental health interventions, achieving an F1 score of 0.34 for exact day detection in a study with 126 workers and 198 rare events.
Rare life events significantly impact mental health, and their detection in behavioral studies is a crucial step towards health-based interventions. We envision that mobile sensing data can be used to detect these anomalies. However, the human-centered nature of the problem, combined with the infrequency and uniqueness of these events makes it challenging for unsupervised machine learning methods. In this paper, we first investigate granger-causality between life events and human behavior using sensing data. Next, we propose a multi-task framework with an unsupervised autoencoder to capture irregular behavior, and an auxiliary sequence predictor that identifies transitions in workplace performance to contextualize events. We perform experiments using data from a mobile sensing study comprising N=126 information workers from multiple industries, spanning 10106 days with 198 rare events (<2%). Through personalized inference, we detect the exact day of a rare event with an F1 of 0.34, demonstrating that our method outperforms several baselines. Finally, we discuss the implications of our work from the context of real-world deployment.